Models of MT and MST areas using wake-sleep algorithm

Authors:
Katsuki Katayama;Masataka Ando;Tsuyoshi Horiguchi
Affiliations:
Research Institute of Electrical Communication, Tohoku University, Sendai 980-8577, Japan;Department of Computer and Mathematical Sciences, GSIS, Tohoku University, Sendai 980-8579, Japan;Department of Computer and Mathematical Sciences, GSIS, Tohoku University, Sendai 980-8579, Japan
Venue:
Neural Networks
Year:
2004

Citing 5
Cited 0

A simple competitive account of some response properties of visual neurons in area MSTd

Neural Computation
A network model for the optic flow computation of the MST neurons

Neural Networks
Self-organizing maps

Self-organizing maps
Factor analysis using delta-rule wake-sleep learning

Neural Computation
Convergence of the wake-sleep algorithm

Proceedings of the 1998 conference on Advances in neural information processing systems II

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present two-layered neural network models with Q(≥2)-states neurons for a system with middle temporal (MT) neurons and medial superior temporal (MST) neurons by using a wake-sleep algorithm proposed by Hinton et al.; we notice that the wake-sleep algorithm consists of local learning rules. We first investigate a model with binary neurons for response properties of the MST neurons to optical flows as for various types of motion. We next extend the model with binary neurons to a model with Q(≥3)-states neurons and investigate the response properties of the MST neurons for various values of Q(≥3). We obtain better response properties for the model with Q(≥3)-states neurons than for the one with binary neurons.